aboutsummaryrefslogtreecommitdiffstats
path: root/libavcodec/x86/idctdsp.asm
blob: 1cfdb5419df94de77dc37900d5c0238c8c3d4046 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
;******************************************************************************
;* SIMD-optimized IDCT-related routines
;* Copyright (c) 2008 Loren Merritt
;* Copyright (c) 2003-2013 Michael Niedermayer
;* Copyright (c) 2013 Daniel Kang
;*
;* This file is part of FFmpeg.
;*
;* FFmpeg is free software; you can redistribute it and/or
;* modify it under the terms of the GNU Lesser General Public
;* License as published by the Free Software Foundation; either
;* version 2.1 of the License, or (at your option) any later version.
;*
;* FFmpeg is distributed in the hope that it will be useful,
;* but WITHOUT ANY WARRANTY; without even the implied warranty of
;* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
;* Lesser General Public License for more details.
;*
;* You should have received a copy of the GNU Lesser General Public
;* License along with FFmpeg; if not, write to the Free Software
;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
;******************************************************************************

%include "libavutil/x86/x86util.asm"

SECTION_RODATA

cextern pb_80

SECTION .text

;--------------------------------------------------------------------------
;void ff_put_signed_pixels_clamped(const int16_t *block, uint8_t *pixels,
;                                  ptrdiff_t line_size)
;--------------------------------------------------------------------------

%macro PUT_SIGNED_PIXELS_CLAMPED_HALF 1
    mova     m1, [blockq+mmsize*0+%1]
    mova     m2, [blockq+mmsize*2+%1]
    packsswb m1, [blockq+mmsize*1+%1]
    packsswb m2, [blockq+mmsize*3+%1]
    paddb    m1, m0
    paddb    m2, m0
    movq     [pixelsq+lsizeq*0], m1
    movhps   [pixelsq+lsizeq*1], m1
    movq     [pixelsq+lsizeq*2], m2
    movhps   [pixelsq+lsize3q ], m2
%endmacro

INIT_XMM sse2
cglobal put_signed_pixels_clamped, 3, 4, 3, block, pixels, lsize, lsize3
    mova     m0, [pb_80]
    lea      lsize3q, [lsizeq*3]
    PUT_SIGNED_PIXELS_CLAMPED_HALF 0
    lea      pixelsq, [pixelsq+lsizeq*4]
    PUT_SIGNED_PIXELS_CLAMPED_HALF 64
    RET

;--------------------------------------------------------------------------
; void ff_put_pixels_clamped(const int16_t *block, uint8_t *pixels,
;                            ptrdiff_t line_size);
;--------------------------------------------------------------------------
; %1 = block offset
%macro PUT_PIXELS_CLAMPED_HALF 1
    mova     m0, [blockq+mmsize*0+%1]
    mova     m1, [blockq+mmsize*2+%1]
    packuswb m0, [blockq+mmsize*1+%1]
    packuswb m1, [blockq+mmsize*3+%1]
    movq           [pixelsq], m0
    movhps  [lsizeq+pixelsq], m0
    movq  [2*lsizeq+pixelsq], m1
    movhps [lsize3q+pixelsq], m1
%endmacro

INIT_XMM sse2
cglobal put_pixels_clamped, 3, 4, 2, block, pixels, lsize, lsize3
    lea lsize3q, [lsizeq*3]
    PUT_PIXELS_CLAMPED_HALF 0
    lea pixelsq, [pixelsq+lsizeq*4]
    PUT_PIXELS_CLAMPED_HALF 64
    RET

;--------------------------------------------------------------------------
; void ff_add_pixels_clamped(const int16_t *block, uint8_t *pixels,
;                            ptrdiff_t line_size);
;--------------------------------------------------------------------------
; %1 = block offset
%macro ADD_PIXELS_CLAMPED 1
    mova       m0, [blockq+mmsize*0+%1]
    mova       m1, [blockq+mmsize*1+%1]
    movq       m2, [pixelsq]
    movq       m3, [pixelsq+lsizeq]
    punpcklbw  m2, m4
    punpcklbw  m3, m4
    paddsw     m0, m2
    paddsw     m1, m3
    packuswb   m0, m1
    movq       [pixelsq], m0
    movhps     [pixelsq+lsizeq], m0
%endmacro

INIT_XMM sse2
cglobal add_pixels_clamped, 3, 3, 5, block, pixels, lsize
    pxor       m4, m4
    ADD_PIXELS_CLAMPED 0
    lea        pixelsq, [pixelsq+lsizeq*2]
    ADD_PIXELS_CLAMPED 32
    lea        pixelsq, [pixelsq+lsizeq*2]
    ADD_PIXELS_CLAMPED 64
    lea        pixelsq, [pixelsq+lsizeq*2]
    ADD_PIXELS_CLAMPED 96
    RET